© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 31251
    Prev
    Next
    INDEX
    Explanations

    adjectives or descriptive terms indicating physical feelings or states

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    374
    +0.09
    0.6%
    447
    +0.09
    0.6%
    241
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.09
    0.26
    578
    +0.09
    0.04
    374
    +0.08
    0.05
    Negative Logits
     Fisheries
    -0.50
    ATTLE
    -0.45
     dissolution
    -0.45
    ENCY
    -0.45
    URRENT
    -0.44
    nce
    -0.42
     consolidation
    -0.42
     Tsarnaev
    -0.41
    BILITY
    -0.41
    XY
    -0.41
    POSITIVE LOGITS
    ilver
    1.02
    hift
    0.95
    haw
    0.78
    mith
    0.77
    awed
    0.73
    heet
    0.67
    ucker
    0.66
    ource
    0.65
    pace
    0.64
    aws
    0.63
    Activations Density 11.480%

    No Known Activations